glm-4.7-flash
by Poe · listed Jan 2026RT
Efficient GLM model for fast reasoning, coding, and agent workflows
Current rates USD per 1M tokens
Input—
Output—
Cache read—
Cache write—
Against the market
On the record
- Model id
novita/glm-4.7-flash- Context window
- 200K tokens
- Max output
- 66K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2026-01-19
- Last updated
- 2026-01-19
Also listed at
- Hugging Facefree in · free out
- Zhipu AIfree in · free out
- Z.AIfree in · free out
- CrofAI$0.04 in · $0.30 out
- LLM Gateway$0.06 in · $0.40 out
- Cloudflare AI Gateway$0.06 in · $0.40 out
- Deep Infra$0.06 in · $0.40 out
- Kilo Gateway$0.06 in · $0.40 out
- OpenRouter$0.06 in · $0.40 out
- Cloudflare Workers AI$0.0605 in · $0.40 out
- Vercel AI Gateway$0.07 in · $0.40 out
- NovitaAI$0.07 in · $0.40 out
- Jiekou.AI$0.07 in · $0.40 out
- NanoGPT$0.07 in · $0.40 out
- Cortecs$0.09 in · $0.53 out